A fault prediction system and method based on a Bayesian belief network

A fault prediction and Bayesian technology, applied in the direction of prediction, based on specific mathematical models, special data processing applications, etc., can solve problems such as fault diagnosis and prediction application problems, and achieve good engineering application value

Inactive Publication Date: 2019-05-17
BEIHANG UNIV
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] There are many methods of fault diagnosis and prediction, but the determination and selection of fault diagnosis and prediction methods involve many factors, such as the type of failure, the form of failu

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A fault prediction system and method based on a Bayesian belief network
  • A fault prediction system and method based on a Bayesian belief network
  • A fault prediction system and method based on a Bayesian belief network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to realize a failure prediction system and method based on Bayesian belief network proposed in the present invention, a certain vehicle active suspension system is selected to demonstrate the embodiment. The system can be transformed into a 12-node Bayesian belief network, the network structure is as follows figure 2 As shown: the active suspension system is composed of passive equipment X2 and hydraulic actuator X3, and the hydraulic actuator is composed of mechanical equipment X4 and electronic equipment X5. The whole system has 7 inseparable bottom parts, which are X6 springs , X7 gate valve, X8 pump and piston system, X9 servo, X10 engine, X11 sensor, X12 regulator.

[0054] The concrete implementation process of the present invention is as image 3 shown. Firstly, analyze the object under test to judge whether the system structure is clear. If not, learn the structure of the system according to the data and then build a Bayesian belief network. If the s...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a fault prediction system and method based on a Bayesian belief network, and the method comprises the steps of building a system mathematical model based on the Bayesian beliefnetwork according to a system structure and internal connection, wherein the model comprises the parameters consisting of a system hierarchical interconnection structure and a condition probability; calculating system failure rate analysis weak links through a Bayesian belief network reasoning engine according to the failure rate of root node components; and according to a reliability correlationformula, predicting the average time before failure of the system. According to the fault prediction system and method based on the Bayesian belief network provided by the invention, for the system with high uncertainty and complex internal interconnection relationship, reliability analysis can be more accurately and quickly carried out on the system, weak links of the system can be found, the fault rate of the system can be calculated, and the service life of the system can be predicted, so that the engineering application value is better.

Description

technical field [0001] The invention relates to a fault prediction system and method based on a Bayesian belief network, belonging to the technical field of fault diagnosis and prediction. Background technique [0002] There are many methods of fault diagnosis and prediction, but the determination and selection of fault diagnosis and prediction methods involve many factors, such as the type of failure, the form of failure mode, the criterion of failure, the method of processing data, and the uncertainty of variables. Considerations and so on, which bring huge problems to the practical application of fault diagnosis and prediction. [0003] Bayesian belief network has many advantages as a modeling analysis method based on statistics. It uses a mathematical model to quantitatively describe the causal relationship and degree of correlation between variables in the form of probability. Moreover, the reasoning of Bayesian belief network is bidirectional, both bottom-up and top-...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N7/00G06F17/50G06Q10/04
Inventor 胡薇薇司田煜孙宇锋赵广燕
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap